How to tune hyperparameters for LSTM training.

8 次查看（过去 30 天）
Badavath Purnesh Singh
回答： David Willingham 2021-11-5
I'm training a LSTM model for signal classificaiton. The training progress graph looks like the first pictiure at the very begininng and incrreases slowy. I think the model is over fitting or unddr fitting. I hope somone could resolve this issue.
  1 个评论
Badavath Purnesh Singh
Badavath Purnesh Singh 2021-11-5
To let the algorithm train upto 95-99%, it is talking 3000 epochs. I have used 0.0001 as Learning rate and default mini batch value.

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

David Willingham
David Willingham 2021-11-5
Hi,
I'd recommend using the Experiment Manager App for tuning / understanding various hyperparameter combinations.
Here is an example of how to use it for a LSTM problem.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

产品


版本

R2021a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by